Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection
arXiv:1902.04980 · doi:10.1109/ICASSP.2019.8682901
Abstract
In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection. By integrating uncertainty into the hidden states, this type of network is able to learn the distribution of complex sequences. Because the learned distribution can be calculated explicitly in terms of probability, we can evaluate how likely an observation is then detect low-probability events as novel. The model is robust, highly unsupervised, end-to-end and requires minimum preprocessing, feature engineering or hyperparameter tuning. An experiment on a benchmark dataset shows that our model outperforms the state-of-the-art acoustic novelty detectors.
arXiv commentAccepted to ICASSP 2019
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- WaveNet: A Generative Model for Raw Audio
- A Recurrent Latent Variable Model for Sequential Data
- Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- Gated Feedback Recurrent Neural Networks
- Learning Stochastic Recurrent Networks
- Sequential Neural Models with Stochastic Layers
- Deep Kalman Filters
- A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams